Responsibilities
- Design CI/CD workflows for model and inference service releases across development, staging, and production environments.
- Own model deployment and runtime operations, including versioning, rollback safety, and release automation.
- Build monitoring for latency, throughput, model health, drift, and failure patterns with actionable alerting.
- Partner with AI and platform teams to optimize inference reliability on local machines.
- Develop reproducible data and evaluation pipelines that support rapid iteration and trustworthy model updates.
- Improve infrastructure for experiment tracking, model registry hygiene, and operational incident response.
Qualifications
- Strong Python and production ML systems experience, including deploying and maintaining model-backed services.
- Hands-on MLOps experience with CI/CD automation, model versioning, and observability tooling.
- Experience with model serving, async processing, queue-based workloads, and reliability engineering practices.
- Working knowledge of model monitoring concepts such as drift, data quality checks, and performance regression detection.
- Comfort collaborating across backend and platform teams in a startup environment.
- Strong ownership mindset and ability to balance speed with operational rigor.